Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/minusblindfold/devloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/minusblindfold/devloop/dl)<a href="https://agentmods.dev/plugins/minusblindfold/devloop/dl"><img src="https://agentmods.dev/badge/plugins/minusblindfold/devloop/dl/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/minusblindfold/devloop/dl"><img src="https://agentmods.dev/badge/plugins/minusblindfold/devloop/dl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "dl",
"description": "Structured development workflow for Claude Code — brainstorm, research, plan, design, implement, review",
"version": "3.3.0",
"author": {
"name": "minusblindfold"
},
"homepage": "https://github.com/minusblindfold/devloop",
"repository": "https://github.com/minusblindfold/devloop",
"license": "MIT",
"keywords": ["workflow", "brainstorm", "planning", "design", "implementation", "review", "skills"],
"hooks": {}
}
What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 218 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 14 lines scan A 8f85cc414c5b
dl is a plugin published in the GitHub repository minusblindfold/devloop (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
context-engineering
Comprehensive toolkit for creating production-ready Claude Code resources: agents, skills, plugins, commands, hooks, MCP tools, MCP servers, and patterns. Expert guidance with templates, examples, and best practices following Anthropic specifications.
databases
Database experts for SQL, NoSQL, graph databases, and vector databases. Includes Postgres, MongoDB, Neo4j, Cassandra, MariaDB, and vector DB specialists.
dev
Development experts for 10 programming languages (Python, TypeScript, JavaScript, Go, Rust, C++, Kotlin, PHP, Lua and Perl), plus FastAPI and Node.js specialists and a refactoring agent.
infrastructure
Infrastructure and DevOps specialists for AWS, GCP, Kubernetes, Docker, Terraform, GitHub Actions, GitLab CI, and security auditing.
research-team
Multi-agent research system for comprehensive topic investigation. The research-team:coordinator skill decomposes a topic into subtopics, spawns parallel research-specialist subagents, and delegates synthesis to a report-writer — all from the main agent thread so nested-spawn constraints don't apply. Reports are plain.
adv
Adversarial multi-model code review and model dispatch. Orchestrates Claude, Codex CLI, and Gemini CLI for cross-examined code review with 5 specialized reviewers.